BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//DevOpsChat//Events//EN
CALSCALE:GREGORIAN
METHOD:PUBLISH
BEGIN:VEVENT
UID:01a1989d-2ca3-7040-97a7-c9ea89200437@www.devopschat.co
DTSTAMP:20261106T132957Z
DTSTART:20200609T173000Z
DTEND:20200609T183000Z
SUMMARY:The anomaly detection I actually wanted
DESCRIPTION:Mean time to resolution (MTTR) is the battleground for customer
  loyalty. But\, it's really hard to reduce MTTR for the "unknown unknowns"
 . A new approach is needed to root-cause and sometimes even to detect nove
 l incidents. Anomaly detection has been implemented by various tools and w
 ith varying degrees of success\, but doesn't rise to the bar of novel inci
 dent recognition.\n\nI've spent the last few years developing a new approa
 ch that uses machine learning to automatically catch and characterize nove
 l software incidents. I will discuss the approach I've taken and show you 
 some real-life examples. The net result is a log-and-metrics-based monitor
 ing system requiring zero human training or configuration\, that recognize
 s and characterizes novel incidents.\n\nhttps://www.devopschat.co/meetings
 /the-anomaly-detection-i-actually-wanted
URL:https://www.devopschat.co/meetings/the-anomaly-detection-i-actually-wan
 ted
END:VEVENT
END:VCALENDAR